From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755227Ab2K2W3Q (ORCPT ); Thu, 29 Nov 2012 17:29:16 -0500 Received: from terminus.zytor.com ([198.137.202.10]:53184 "EHLO mail.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754823Ab2K2W3P (ORCPT ); Thu, 29 Nov 2012 17:29:15 -0500 Message-ID: <50B7E17A.2020609@zytor.com> Date: Thu, 29 Nov 2012 14:28:10 -0800 From: "H. Peter Anvin" User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/17.0 Thunderbird/17.0 MIME-Version: 1.0 To: Andi Kleen CC: Jim Kukunas , Linux Raid , Linux Kernel , Neil Brown Subject: Re: [PATCH] lib/raid6: Add AVX2 optimized recovery functions References: <1352411264-5156-1-git-send-email-james.t.kukunas@linux.intel.com> <50B7CFF8.7010401@zytor.com> <20121129211828.GZ16230@one.firstfloor.org> In-Reply-To: <20121129211828.GZ16230@one.firstfloor.org> X-Enigmail-Version: 1.4.6 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 11/29/2012 01:18 PM, Andi Kleen wrote: > >> Either way, this implementatin technique was used for the MMX/SSE >> implementations without any problems for 9 years now. > > It's still wrong. > > Lying to the compiler usually bites you at some point. > It's not lying to the compiler. It is telling the compiler "do something that you have no way of knowing about". It would be lying to the compiler if the compiler was allowed to touch the FPU state, but it's not. -hpa